Emotion Space Online Assistance

These Human facial expressions convey a lot of information visually rather than articulately. Facial expression recognition plays a crucial role in the area of human-machine interaction. Automatic facial expression recognition system has many applications including, but not limited to, human behavior understanding, detection of mental disorders, and synthetic human expressions. Recognition of facial expression by computer with high recognition rate is still a challenging task. Two popular methods utilized mostly in the literature for the automatic FER systems are based on geometry and appearance. Facial Expression Recognition usually performed in four-stages consisting of pre-processing, face detection, feature extraction, and expression classification. In this project we applied various deep learning methods (convolutional neural networks) to identify the key seven human emotions: anger, disgust, fear, happiness, sadness, surprise and neutrality. The primary Aim of this project was to develop an emotion recognition web-application that was capable of recognising emotions expressed by people in a video stream but could also be deployed to run natively on embedded devices. Current solutions revolve around deep learning techniques which require a great deal of processing. This means that when embedded devices are used, they function primarily as an input video source for a remote server that carries out the processing. The web-application developed had to be capable of recording a video stream and detecting the emotions expressed in it. The detected emotions had to then be displayable in a meaningful manner in order to give insights into the emotions expressed by people being recorded. This could then be used by marketing professionals to gain truthful information about how people feel when watching an advert or having a product demonstrated to them. With the emotion recognition system, AI can detect the emotions of a person through their facial expressions. Detected